Menu
Use for non-trivial implementation work. Delegate the coding or large-repo analysis to Codex CLI, then record usage before handing back results.
Install with Codex or Claude Copy this prompt, paste it into Codex, Claude, or another assistant, and let it review the skill page and install it for you.
Based on SOC occupation classification
Use for Gitea, GitOps, registry, and every non-trivial implementation task that should be delegated to Codex instead of being coded inline.
Browse in-cluster Gitea repos, issues, pull requests, commits, chart values, GitOps definitions, and sandbox image sources for read-only design context with the `__REVIEWER_GITEA_USERNAME__` Gitea user shared with auditor.
Review in-cluster Gitea repos and pull requests by reading files, inspecting diffs, checking comments, posting review feedback, and approving with the `__REVIEWER_GITEA_USERNAME__` Gitea user shared with architect; merge only with explicit instruction.
Use this to turn recent Qdrant memories and changed Nextcloud docs into clean Memgraph links, Qdrant graph-link annotations, and an updated grooming checkpoint.
Use when routing work to a standing specialist or reviewing a specialist return.
Use when operating Nextcloud as the shared coordination layer for desk state, calendars, todos, tables, sharing, or coordination status.
| name | run-codex-and-log-usage |
| description | Use for non-trivial implementation work. Delegate the coding or large-repo analysis to Codex CLI, then record usage before handing back results. |
Use this skill whenever the task involves meaningful code generation, refactoring, debugging, or broad codebase analysis.
openclaw-codex-run -- "..." for non-trivial Codex workopenclaw-codex-run --elevated -- "..." only for extra complex tasks or unusually large codebasestmux session by default and records run state under /workspace/.home/.local/state/openclaw-codex-runs/openclaw-codex-run --status <run-id>, --tail <run-id>, and --wait <run-id> to monitor the run instead of assuming the surrounding OpenClaw exec session is the lifecycle boundaryopenclaw-codex-run --foreground -- "..." only for short diagnostic runs where an outer timeout cannot kill useful work~/.openclaw/gpt-5.3-codex for implementation workgpt-5.5 for extra complex debugging loops, broad refactors, or unfamiliar large codebasestokscale is the source of truth for usage metrics in this stackopenclaw-codex-run captures Codex --json output under /workspace/.home/.config/tokscale/headless/codex/ and writes a per-run Tokscale report path in its status JSONestimated_cost_usd to be present in raw Codex JSONL/Projects/ai-homebase/codex-usage/YYYY-MM-DD.jsontimestamp, model, input_tokens, output_tokens, cache_read_tokens when available, estimated_cost_usd, task_summary, run_id, jsonl_path, usage_report_path, and codex_flagsKeep direct ownership of: